config.json

{
  "architectures": [
    "EncoderDecoderModel"
  ],
  "decoder": {
    "_name_or_path": "hf-internal-testing/tiny-random-gpt2",
    "activation_function": "gelu_new",
    "add_cross_attention": true,
    "attention_probs_dropout_prob": 0.1,
    "attn_pdrop": 0.1,
    "bos_token_id": 98,
    "embd_pdrop": 0.1,
    "eos_token_id": 98,
    "gradient_checkpointing": false,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "initializer_range": 0.02,
    "intermediate_size": 37,
    "is_decoder": true,
    "layer_norm_epsilon": 1e-05,
    "model_type": "gpt2",
    "n_ctx": 512,
    "n_embd": 32,
    "n_head": 4,
    "n_inner": null,
    "n_layer": 5,
    "n_positions": 512,
    "pad_token_id": 98,
    "reorder_and_upcast_attn": false,
    "resid_pdrop": 0.1,
    "scale_attn_by_inverse_layer_idx": false,
    "scale_attn_weights": true,
    "summary_activation": null,
    "summary_first_dropout": 0.1,
    "summary_proj_to_labels": true,
    "summary_type": "cls_index",
    "summary_use_proj": true,
    "torch_dtype": "float32",
    "type_vocab_size": 16,
    "use_cache": true,
    "vocab_size": 1000
  },
  "encoder": {
    "_name_or_path": "hf-internal-testing/tiny-random-bert",
    "attention_probs_dropout_prob": 0.1,
    "classifier_dropout": null,
    "gradient_checkpointing": false,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 32,
    "initializer_range": 0.02,
    "intermediate_size": 37,
    "layer_norm_eps": 1e-12,
    "max_position_embeddings": 512,
    "model_type": "bert",
    "num_attention_heads": 4,
    "num_hidden_layers": 5,
    "position_embedding_type": "absolute",
    "torch_dtype": "float32",
    "type_vocab_size": 16,
    "use_cache": true,
    "vocab_size": 1124
  },
  "is_encoder_decoder": true,
  "model_type": "encoder-decoder",
  "torch_dtype": "float32",
  "transformers_version": "4.53.3"
}